diff mbox

[rs6000,generic,builtins] Fix unary TDmode patterns and add DFP ABS builtins

Message ID 1376692337.5807.36.camel@otta
State New
Headers show

Commit Message

Peter Bergner Aug. 16, 2013, 10:32 p.m. UTC 
On Fri, 2013-08-16 at 23:25 +0200, Jakub Jelinek wrote:
> On Fri, Aug 16, 2013 at 04:18:18PM -0500, Peter Bergner wrote:
> > --- gcc/config/rs6000/dfp.md	(revision 201779)
> > +++ gcc/config/rs6000/dfp.md	(working copy)
> > @@ -132,11 +132,14 @@ (define_expand "negtd2"
> >    "")
> >  
> >  (define_insn "*negtd2_fpr"
> > -  [(set (match_operand:TD 0 "gpc_reg_operand" "=d")
> > -	(neg:TD (match_operand:TD 1 "gpc_reg_operand" "d")))]
> > +  [(set (match_operand:TD 0 "gpc_reg_operand" "=d,d")
> > +	(neg:TD (match_operand:TD 1 "gpc_reg_operand" "d,0")))]
> 
> I'm surprised if it works in this order, I'd expect that alternative 0
> would match even for the same regno and that the second alternative wouldn't
> be tried.

Ok, updated to switch the order of the alternatives.  This works...just
like the previous one.  I created two versions of the TD test case to
test both alternatives and to make sure we get fmrs on the one and
no fmrs on the other.

Peter


gcc/
        * builtins.def (BUILT_IN_FABSD32): New DFP ABS builtin.
        (BUILT_IN_FABSD64): Likewise.
        (BUILT_IN_FABSD128): Likewise.
        * builtins.c (expand_builtin): Add support for new DFP ABS builtins.
        (fold_builtin_1): Likewise.
        * config/rs6000/dfp.md (*negtd2_fpr): Handle non-overlapping destination
        and source operands.
        (*abstd2_fpr): Likewise.
        (*nabstd2_fpr): Likewise.

gcc/testsuite/
        * gcc.target/powerpc/dfp-dd-2.c: New test.
        * gcc.target/powerpc/dfp-td-2.c: Likewise.
	* gcc.target/powerpc/dfp-td-3.c: Likewise.

Comments

Peter Bergner Aug. 17, 2013, 12:19 a.m. UTC | #1 
On Fri, 2013-08-16 at 17:32 -0500, Peter Bergner wrote:
> Ok, updated to switch the order of the alternatives.  This works...just
> like the previous one.  I created two versions of the TD test case to
> test both alternatives and to make sure we get fmrs on the one and
> no fmrs on the other.

FYI, this did bootstrap and regtest with no errors.  Ok for mainline?
And is the *negtd2_fpr hunk ok for the 4.8 branch?

Peter
David Edelsohn Aug. 19, 2013, 1:17 p.m. UTC | #2 
On Fri, Aug 16, 2013 at 6:32 PM, Peter Bergner <bergner@vnet.ibm.com> wrote:

> Ok, updated to switch the order of the alternatives.  This works...just
> like the previous one.  I created two versions of the TD test case to
> test both alternatives and to make sure we get fmrs on the one and
> no fmrs on the other.
>
> Peter
>
>
> gcc/
>         * builtins.def (BUILT_IN_FABSD32): New DFP ABS builtin.
>         (BUILT_IN_FABSD64): Likewise.
>         (BUILT_IN_FABSD128): Likewise.
>         * builtins.c (expand_builtin): Add support for new DFP ABS builtins.
>         (fold_builtin_1): Likewise.
>         * config/rs6000/dfp.md (*negtd2_fpr): Handle non-overlapping destination
>         and source operands.
>         (*abstd2_fpr): Likewise.
>         (*nabstd2_fpr): Likewise.
>
> gcc/testsuite/
>         * gcc.target/powerpc/dfp-dd-2.c: New test.
>         * gcc.target/powerpc/dfp-td-2.c: Likewise.
>         * gcc.target/powerpc/dfp-td-3.c: Likewise.

The last version is okay.

> And is the *negtd2_fpr hunk ok for the 4.8 branch?

The negtd2_fpr change is okay for the 4.8 branch.

Thanks, David
Peter Bergner Aug. 19, 2013, 5:57 p.m. UTC | #3 
On Mon, 2013-08-19 at 09:17 -0400, David Edelsohn wrote:
> The last version is okay.

Jakub ack'd the builtins.{c,def] changes on IRC, so I have committed
this as revision 201849.


> > And is the *negtd2_fpr hunk ok for the 4.8 branch?
> 
> The negtd2_fpr change is okay for the 4.8 branch.

...and this as revision 201850.

Thank you Jakub and David!

Peter
diff mbox

Patch

Index: gcc/builtins.c
===================================================================
--- gcc/builtins.c	(revision 201779)
+++ gcc/builtins.c	(working copy)
@@ -5865,6 +5865,9 @@  expand_builtin (tree exp, rtx target, rt
   switch (fcode)
     {
     CASE_FLT_FN (BUILT_IN_FABS):
+    case BUILT_IN_FABSD32:
+    case BUILT_IN_FABSD64:
+    case BUILT_IN_FABSD128:
       target = expand_builtin_fabs (exp, target, subtarget);
       if (target)
 	return target;
@@ -10314,6 +10317,9 @@  fold_builtin_1 (location_t loc, tree fnd
       return fold_builtin_strlen (loc, type, arg0);
 
     CASE_FLT_FN (BUILT_IN_FABS):
+    case BUILT_IN_FABSD32:
+    case BUILT_IN_FABSD64:
+    case BUILT_IN_FABSD128:
       return fold_builtin_fabs (loc, arg0, type);
 
     case BUILT_IN_ABS:
Index: gcc/builtins.def
===================================================================
--- gcc/builtins.def	(revision 201779)
+++ gcc/builtins.def	(working copy)
@@ -257,6 +257,9 @@  DEF_C99_BUILTIN        (BUILT_IN_EXPM1L,
 DEF_LIB_BUILTIN        (BUILT_IN_FABS, "fabs", BT_FN_DOUBLE_DOUBLE, ATTR_CONST_NOTHROW_LEAF_LIST)
 DEF_C99_C90RES_BUILTIN (BUILT_IN_FABSF, "fabsf", BT_FN_FLOAT_FLOAT, ATTR_CONST_NOTHROW_LEAF_LIST)
 DEF_C99_C90RES_BUILTIN (BUILT_IN_FABSL, "fabsl", BT_FN_LONGDOUBLE_LONGDOUBLE, ATTR_CONST_NOTHROW_LEAF_LIST)
+DEF_GCC_BUILTIN        (BUILT_IN_FABSD32, "fabsd32", BT_FN_DFLOAT32_DFLOAT32, ATTR_CONST_NOTHROW_LEAF_LIST)
+DEF_GCC_BUILTIN        (BUILT_IN_FABSD64, "fabsd64", BT_FN_DFLOAT64_DFLOAT64, ATTR_CONST_NOTHROW_LEAF_LIST)
+DEF_GCC_BUILTIN        (BUILT_IN_FABSD128, "fabsd128", BT_FN_DFLOAT128_DFLOAT128, ATTR_CONST_NOTHROW_LEAF_LIST)
 DEF_C99_BUILTIN        (BUILT_IN_FDIM, "fdim", BT_FN_DOUBLE_DOUBLE_DOUBLE, ATTR_MATHFN_FPROUNDING_ERRNO)
 DEF_C99_BUILTIN        (BUILT_IN_FDIMF, "fdimf", BT_FN_FLOAT_FLOAT_FLOAT, ATTR_MATHFN_FPROUNDING_ERRNO)
 DEF_C99_BUILTIN        (BUILT_IN_FDIML, "fdiml", BT_FN_LONGDOUBLE_LONGDOUBLE_LONGDOUBLE, ATTR_MATHFN_FPROUNDING_ERRNO)
Index: gcc/config/rs6000/dfp.md
===================================================================
--- gcc/config/rs6000/dfp.md	(revision 201779)
+++ gcc/config/rs6000/dfp.md	(working copy)
@@ -132,11 +132,14 @@  (define_expand "negtd2"
   "")
 
 (define_insn "*negtd2_fpr"
-  [(set (match_operand:TD 0 "gpc_reg_operand" "=d")
-	(neg:TD (match_operand:TD 1 "gpc_reg_operand" "d")))]
+  [(set (match_operand:TD 0 "gpc_reg_operand" "=d,d")
+	(neg:TD (match_operand:TD 1 "gpc_reg_operand" "0,d")))]
   "TARGET_HARD_FLOAT && TARGET_FPRS"
-  "fneg %0,%1"
-  [(set_attr "type" "fp")])
+  "@
+   fneg %0,%1
+   fneg %0,%1\;fmr %L0,%L1"
+  [(set_attr "type" "fp")
+   (set_attr "length" "4,8")])
 
 (define_expand "abstd2"
   [(set (match_operand:TD 0 "gpc_reg_operand" "")
@@ -145,18 +148,24 @@  (define_expand "abstd2"
   "")
 
 (define_insn "*abstd2_fpr"
-  [(set (match_operand:TD 0 "gpc_reg_operand" "=d")
-	(abs:TD (match_operand:TD 1 "gpc_reg_operand" "d")))]
+  [(set (match_operand:TD 0 "gpc_reg_operand" "=d,d")
+	(abs:TD (match_operand:TD 1 "gpc_reg_operand" "0,d")))]
   "TARGET_HARD_FLOAT && TARGET_FPRS"
-  "fabs %0,%1"
-  [(set_attr "type" "fp")])
+  "@
+   fabs %0,%1
+   fabs %0,%1\;fmr %L0,%L1"
+  [(set_attr "type" "fp")
+   (set_attr "length" "4,8")])
 
 (define_insn "*nabstd2_fpr"
-  [(set (match_operand:TD 0 "gpc_reg_operand" "=d")
-	(neg:TD (abs:TD (match_operand:TD 1 "gpc_reg_operand" "d"))))]
+  [(set (match_operand:TD 0 "gpc_reg_operand" "=d,d")
+	(neg:TD (abs:TD (match_operand:TD 1 "gpc_reg_operand" "0,d"))))]
   "TARGET_HARD_FLOAT && TARGET_FPRS"
-  "fnabs %0,%1"
-  [(set_attr "type" "fp")])
+  "@
+   fnabs %0,%1
+   fnabs %0,%1\;fmr %L0,%L1"
+  [(set_attr "type" "fp")
+   (set_attr "length" "4,8")])
 
 ;; Hardware support for decimal floating point operations.
 
Index: gcc/testsuite/gcc.target/powerpc/dfp-dd-2.c
===================================================================
--- gcc/testsuite/gcc.target/powerpc/dfp-dd-2.c	(revision 0)
+++ gcc/testsuite/gcc.target/powerpc/dfp-dd-2.c	(revision 0)
@@ -0,0 +1,26 @@ 
+/* Test generation of DFP instructions for POWER6.  */
+/* { dg-do compile { target { powerpc*-*-linux* && powerpc_fprs } } } */
+/* { dg-options "-std=gnu99 -O1 -mcpu=power6" } */
+
+/* { dg-final { scan-assembler-times "fneg" 1 } } */
+/* { dg-final { scan-assembler-times "fabs" 1 } } */
+/* { dg-final { scan-assembler-times "fnabs" 1 } } */
+/* { dg-final { scan-assembler-times "fmr" 0 } } */
+
+_Decimal64
+func1 (_Decimal64 a, _Decimal64 b)
+{
+  return -b;
+}
+
+_Decimal64
+func2 (_Decimal64 a, _Decimal64 b)
+{
+  return __builtin_fabsd64 (b);
+}
+
+_Decimal64
+func3 (_Decimal64 a, _Decimal64 b)
+{
+  return - __builtin_fabsd64 (b);
+}
Index: gcc/testsuite/gcc.target/powerpc/dfp-td-2.c
===================================================================
--- gcc/testsuite/gcc.target/powerpc/dfp-td-2.c	(revision 0)
+++ gcc/testsuite/gcc.target/powerpc/dfp-td-2.c	(revision 0)
@@ -0,0 +1,29 @@ 
+/* Test generation of DFP instructions for POWER6.  */
+/* { dg-do compile { target { powerpc*-*-linux* && powerpc_fprs } } } */
+/* { dg-options "-std=gnu99 -O1 -mcpu=power6" } */
+
+/* { dg-final { scan-assembler-times "fneg" 1 } } */
+/* { dg-final { scan-assembler-times "fabs" 1 } } */
+/* { dg-final { scan-assembler-times "fnabs" 1 } } */
+/* { dg-final { scan-assembler-times "fmr" 0 } } */
+
+/* These tests verify we only generate fneg, fabs and fnabs
+   instructions and no fmr's since these are done in place.  */
+
+_Decimal128
+func1 (_Decimal128 a)
+{
+  return -a;
+}
+
+_Decimal128
+func2 (_Decimal128 a)
+{
+  return __builtin_fabsd128 (a);
+}
+
+_Decimal128
+func3 (_Decimal128 a)
+{
+  return - __builtin_fabsd128 (a);
+}
Index: gcc/testsuite/gcc.target/powerpc/dfp-td-3.c
===================================================================
--- gcc/testsuite/gcc.target/powerpc/dfp-td-3.c	(revision 0)
+++ gcc/testsuite/gcc.target/powerpc/dfp-td-3.c	(revision 0)
@@ -0,0 +1,29 @@ 
+/* Test generation of DFP instructions for POWER6.  */
+/* { dg-do compile { target { powerpc*-*-linux* && powerpc_fprs } } } */
+/* { dg-options "-std=gnu99 -O1 -mcpu=power6" } */
+
+/* { dg-final { scan-assembler-times "fneg" 1 } } */
+/* { dg-final { scan-assembler-times "fabs" 1 } } */
+/* { dg-final { scan-assembler-times "fnabs" 1 } } */
+/* { dg-final { scan-assembler-times "fmr" 3 } } */
+
+/* These tests verify we generate fneg, fabs and fnabs and
+   associated fmr's since these are not done in place.  */
+
+_Decimal128
+func1 (_Decimal128 a, _Decimal128 b)
+{
+  return -b;
+}
+
+_Decimal128
+func2 (_Decimal128 a, _Decimal128 b)
+{
+  return __builtin_fabsd128 (b);
+}
+
+_Decimal128
+func3 (_Decimal128 a, _Decimal128 b)
+{
+  return - __builtin_fabsd128 (b);
+}